ActionGuard Protocol Inspector Agent
v1.0.0
io.github.lsendel/actionguard
Diff and poisoning detection for MCP servers: catch schema drift and prompt poisoning.
“Prompt Injection” 共 444 个结果
v1.0.0
io.github.lsendel/actionguard
Diff and poisoning detection for MCP servers: catch schema drift and prompt poisoning.
v1.1.0
com.wordtoclip/mcp
Find any Andrew Tate quote by word and render a captioned vertical clip in one prompt. Unofficial.
v0.3.0
io.github.hydope/shortsmash
Generate finished short videos from a prompt, fetch trends, and check project status via MCP.
v1.0.1
io.github.alphaparkinc/genpark-context-window-token-pruner-skill
Priority-weighted context window token pruner and FIFO eviction engine protecting LLM prompt boundar
v1.0.0
ai.creatify/ad-agent
Turn a prompt, product link, or reference ad into a finished video ad via Creatify's Ad Agent.
v1.0.0
io.github.stand-out-of-my-sun/diogenes-dev-utilities-mcp
JSON healing, O(n) ReDoS defense, XML prompt compilation, and schema verification tools.
v1.0.0
io.github.stand-out-of-my-sun/diogenes-agent-guardrails-mcp
Autonomous agent guardrails, bash sandboxing, MCP rugpull diffing & prompt firewalls.
v0.2.2
io.github.jeannicolasdavid1979/verdictl402
Ask if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples.
v0.2.0
io.github.jeannicolasdavid1979/verdict-mcp
Ask if an action is safe before your agent runs it: injection, shell, MCP installs. Free samples.
v0.4.1
io.github.nika110/openhuddle
Multiplayer mode for AI coding agents: team huddles, master prompt, task board, file claims.
v1.1.0
ai.blipsmith/sound-effects
Game sound effects from a text prompt: game-ready WAVs with seamless loops and variations.
v1.0.0
ai.openmark/openmark
Benchmark your own prompt on 100+ LLMs with real API calls; pick the cheapest model that passes.
v0.1.2
dev.workers.mike-tusa.smugglecheck/smugglecheck
Find hidden prompt-injection text: ASCII smuggling, zero-width/emoji stego, bidi, homoglyphs.
v4.0.0
com.run402.apishield-waf/mcp
50-vector prompt-injection, llms.txt poisoning, SSRF & OpenAPI scanner ($1 USDC).
v0.109.0
io.github.msaad00/agent-bom
面向智能体基础设施的安全扫描与依赖图谱:智能体、MCP、运行时与影响半径。
v1.0.1
ai.koppar/koppar
Design a KiCad PCB from a prompt: parts, schematic checks, routing, KiCad DRC and Gerbers.
v0.1.1
io.github.TAM-DS/guardrails-mcp
Local prompt regression tracker with six fictional cases and evidence for human review.
v0.5.0
ai.mails/agent-email
A real inbox for AI agents: send, receive and thread email, behind a prompt-injection firewall.
v0.1.0
ai.veida/veida-mcp
Generate AI images from a prompt with no API key, using Veida's anonymous free tier.
v1.0.2
io.github.ak10082247-max/canaryguard-402
Deterministic prompt-injection detection & sanitization for AI agents via x402 on Base.
v1.0.2
com.professionalaiagents/seneca
One prompt. ~100 independent AI models. One report: consensus, disagreements, and minority insights.
v1.1.1
io.github.smrht/muziekmakenmetai
Make an original song from a prompt or your own lyrics. Two versions per song, MP3 download.
v1.0.0
io.github.djedi/slimlytics
Privacy-first cookieless web analytics with agent one-prompt setup via remote MCP OAuth.
v0.1.0
kr.co.klisten.api/failbox
Persist failure simulations. No external fault injection or transfers. Customer key required.